Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4638
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to organizations and titles

    oai_token-act-pair · gpt-3.5-turbo

    titles and positions of individuals in organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.73
    blance
    -0.67
    >>>>
    -0.67
     guiActiveUnfocused
    -0.66
    OTA
    -0.65
    acters
    -0.63
     agre
    -0.62
     destro
    -0.62
    zers
    -0.61
    umption
    -0.60
    POSITIVE LOGITS
     coordinator
    0.83
     attorney
    0.79
     director
    0.79
     Fellow
    0.75
     curator
    0.75
     Coordinator
    0.74
     liaison
    0.73
     deputy
    0.72
     planner
    0.71
     representative
    0.71
    Activations Density 0.380%

    No Known Activations